i'm just an advisor, cant take credit. team is doing great with devin 3.0 and devin desktop
AUTOMATION
-
Internal Manual for Building AI Agent Skills Published
By
–
We've published our internal manual for building agent skills. Skills require a new way of thinking for developers.
-

SkillOS: Skill Curation for Self-Evolving Agents
By
–
SkillOS Learning Skill Curation for Self-Evolving Agents paper: https://
huggingface.co/papers/2605.06
614
… -

Unified Evolution of AI-Augmented Agents via Reinforcement Learning
By
–
Skill1 Unified Evolution of Skill-Augmented Agents via Reinforcement Learning paper:
https://huggingface.co/papers/2605.06130
… -
AI tokens wasted on shell command outputs, not code
By
–
90% of the tokens your AI burns aren't from your code.
— AlphaSignal AI (@AlphaSignalAI) 8 mai 2026
Every shell command your agent runs returns raw output.
`git status`, `find`, and `ls` are all read by the LLM in every single run.
A single `playwright test` run dumped enough output to consume 8,100 tokens.
Two… pic.twitter.com/yX1u9lcBo290% of the tokens your AI burns aren't from your code. Every shell command your agent runs returns raw output. `git status`, `find`, and `ls` are all read by the LLM in every single run. A single `playwright test` run dumped enough output to consume 8,100 tokens. Two
-

HuggingFace releases autonomous ML engineer
By
–
HuggingFace released ml-intern, an autonomous ML engineer! ml-intern is an agent that reads papers, writes ML code, trains models, and ships production-ready models using the Hugging Face ecosystem. The workflow: You give it a task like "fine-tune Llama on my dataset." It
-
Telegram Integrates AI Bots and Personal Assistants for Enhanced User Interaction
By
–
Telegram is slowly becoming the most AI-integrated messenger!
— 🚨 AI News | TestingCatalog (@testingcatalog) 8 mai 2026
Users can now interact with guest AI bots, build automated workflows involving bot-to-bot communication, and attach their personal AI assistants to their profiles so the bot can handle incoming inquiries.
Son of… https://t.co/03ZSnULMGr pic.twitter.com/mA8NlWguozTelegram is slowly becoming the most AI-integrated messenger! Users can now interact with guest AI bots, build automated workflows involving bot-to-bot communication, and attach their personal AI assistants to their profiles so the bot can handle incoming inquiries. Son of
-
Technical Workshop on Deploying and Managing AI Agents
By
–
In this meet-up, we'll cover how to: Deploy agents with durable execution so runs survive crashes, deploys, and long waits for human input Use checkpoints and memory stores Add human-in-the-loop gates for consequential decisions We'll also discuss how teams
-
Anthropics co-founder predicts autonomous self-improving AI by 2028
By
–
Anthropics co-founder Jack Clark:
— Chubby♨️ (@kimmonismus) 8 mai 2026
"My prediction is that by the end of 2028, it is more likely than not that we will have an AI system where you could say to it:
"Make a better version of yourself."
And it would simply go off and do that completely autonomously."
Its coming. pic.twitter.com/OEM7zwcQzcAnthropics co-founder Jack Clark: "My prediction is that by the end of 2028, it is more likely than not that we will have an AI system where you could say to it: "Make a better version of yourself." And it would simply go off and do that completely autonomously." Its coming.
-

Mirage unifies backends into one virtual filesystem for AI agents
By
–
AI agents just got one virtual filesystem across every backend. Mirage mounts S3, Drive, Slack, Gmail, GitHub, Linear, Notion, and Postgres under a single root. Agents read and write across them using the same bash commands every model already knows. The team rewrote bash